diff options
author | felix <m.p.isaev@yandex.com> | 2014-12-07 11:52:03 +0100 |
---|---|---|
committer | felix <m.p.isaev@yandex.com> | 2014-12-08 17:01:22 +0100 |
commit | ce36339575da408c5d795f691d07d2e310292b28 (patch) | |
tree | 5f105234e98837d991d705187e10376ffe15b56e | |
parent | 684712076f1ade9dbe432ad95d5796ec278b73ce (diff) |
add teamfourstar.com support
-rw-r--r-- | youtube_dl/extractor/screenwavemedia.py | 32 |
1 files changed, 32 insertions, 0 deletions
diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py index 3fb3bfa32..cf9b8e0de 100644 --- a/youtube_dl/extractor/screenwavemedia.py +++ b/youtube_dl/extractor/screenwavemedia.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..utils import ( ExtractorError, + month_by_name, int_or_none, ) @@ -13,6 +14,7 @@ class ScreenwaveMediaIE(InfoExtractor): _VALID_URL = r'(?:http://)?(?' \ r':(?P<generic>player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<video_id>.+))' \ r'|(?P<cinemassacre>(?:www\.)?cinemassacre\.com/(?P<cm_date_Y>[0-9]{4})/(?P<cm_date_m>[0-9]{2})/(?P<cm_date_d>[0-9]{2})/(?P<cm_display_id>[^?#/]+))' \ + r'|(?P<teamfourstar>(?:www\.)?teamfourstar\.com/video/(?P<tfs_display_id>[a-z0-9\-]+)/?)' \ r')' _TESTS = [ @@ -65,6 +67,34 @@ class ScreenwaveMediaIE(InfoExtractor): '_embed_url': playerdata_url, } + def _teamfourstar_get_info(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('tfs_display_id') + webpage = self._download_webpage(url, display_id) + + mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', webpage) + if not mobj: + raise ExtractorError('Can\'t extract embed url and video id') + playerdata_url = mobj.group('embed_url') + + video_title = self._html_search_regex( + r'<div class="heroheadingtitle">(?P<title>.+?)</div>', webpage, 'title') + video_date = self._html_search_regex( + r'<div class="heroheadingdate">(?P<date>.+?)</div>', webpage, 'date') + mobj = re.match('(?P<month>[A-Z][a-z]+) (?P<day>\d+), (?P<year>\d+)', video_date) + video_date = '%04u%02u%02u' % (int(mobj.group('year')), month_by_name(mobj.group('month')), int(mobj.group('day'))) + video_description = self._html_search_regex( + r'<div class="postcontent">(?P<description>.+?)</div>', webpage, 'description', flags=re.DOTALL) + video_thumbnail = self._og_search_thumbnail(webpage) + + return { + 'title': video_title, + 'description': video_description, + 'upload_date': video_date, + 'thumbnail': video_thumbnail, + '_embed_url': playerdata_url, + } + def _screenwavemedia_get_info(self, url): mobj = re.match(self._VALID_URL, url) if not mobj: @@ -148,6 +178,8 @@ class ScreenwaveMediaIE(InfoExtractor): if mobj: if mobj.group('cinemassacre'): site_info = self._cinemassacre_get_info(url) + elif mobj.group('teamfourstar'): + site_info = self._teamfourstar_get_info(url) if not swm_info: if site_info: |